3D point cloud-based place recognition: a survey

Luo, Kan; Yu, Hongshan; Chen, Xieyuanli; Yang, Zhengeng; Wang, Jingwen; Cheng, Panfei; Mian, Ajmal

doi:10.1007/s10462-024-10713-6

Cited by 3 publications

(2 citation statements)

References 161 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…True loop closure reduces [30] the cumulative position errors caused by visual odometers and builds accurate and consistent maps. The LCD can also be regarded as place recognition [1] and is an important part of VSLAM systems [31]. This problem involves giving a location image and determining whether the place exists in the location database.…”

Section: Application Of Vpr In Vslammentioning

confidence: 99%

See 1 more Smart Citation

BinVPR: Binary Neural Networks towards Real-Valued for Visual Place Recognition

Wang,

Han,

Dong

et al. 2024

Sensors

View full text Add to dashboard Cite

Visual Place Recognition (VPR) aims to determine whether a robot or visual navigation system locates in a previously visited place using visual information. It is an essential technology and challenging problem in computer vision and robotic communities. Recently, numerous works have demonstrated that the performance of Convolutional Neural Network (CNN)-based VPR is superior to that of traditional methods. However, with a huge number of parameters, large memory storage is necessary for these CNN models. It is a great challenge for mobile robot platforms equipped with limited resources. Fortunately, Binary Neural Networks (BNNs) can reduce memory consumption by converting weights and activation values from 32-bit into 1-bit. But current BNNs always suffer from gradients vanishing and a marked drop in accuracy. Therefore, this work proposed a BinVPR model to handle this issue. The solution is twofold. Firstly, a feature restoration strategy was explored to add features into the latter convolutional layers to further solve the gradient-vanishing problem during the training process. Moreover, we identified two principles to address gradient vanishing: restoring basic features and restoring basic features from higher to lower layers. Secondly, considering the marked drop in accuracy results from gradient mismatch during backpropagation, this work optimized the combination of binarized activation and binarized weight functions in the Larq framework, and the best combination was obtained. The performance of BinVPR was validated on public datasets. The experimental results show that it outperforms state-of-the-art BNN-based approaches and full-precision networks of AlexNet and ResNet in terms of both recognition accuracy and model size. It is worth mentioning that BinVPR achieves the same accuracy with only 1% and 4.6% model sizes of AlexNet and ResNet.

show abstract

Section: Application Of Vpr In Vslammentioning

confidence: 99%

“…Visual Place Recognition (VPR) uses visual information to determine whether a robot or autonomous agent has previously visited a place [1]. VPR is an essential technology for robot localization and navigation [2].…”

Section: Introductionmentioning

confidence: 99%

BinVPR: Binary Neural Networks towards Real-Valued for Visual Place Recognition

Wang,

Han,

Dong

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

An Efficient 3D Point Cloud‐Based Place Recognition Approach for Underground Tunnels Using Convolution and Self‐Attention Mechanism

Ye,

Liu,

Yan

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

Existing place recognition methods overly rely on effective geometric features in the data. When directly applied to underground tunnels with repetitive spatial structures and blurry texture features, these methods may result in potential misjudgments, thereby reducing positioning accuracy. Additionally, the substantial computational demands of current methods make it challenging to support real‐time feedback of positioning information. To address the challenges mentioned above, we first introduced the Feature Reconstruction Convolution Module, aimed at reconstructing prevalent similar feature patterns in underground tunnels and aggregating discriminative feature descriptors, thereby enhancing environmental discrimination. Subsequently, the Sinusoidal Self‐Attention Module was implemented to actively filter local descriptors, allocate weights to different descriptors, and determine the most valuable feature descriptors in the network. Finally, the network was further enhanced with the integration of the Rotation‐Equivariant Downsampling Module, designed to expand the receptive field, merge features, and reduce computational complexity. According to experimental results, our algorithm achieves a maximum score of 0.996 on the SubT‐Tunnel data set and 0.995 on the KITTI data set. Moreover, the method only consists of 0.78 million parameters, and the computation time for a single point cloud frame is 17.3 ms. These scores surpass the performance of many advanced algorithms, emphasizing the effectiveness of our approach.

show abstract